CN114466407A - Network slice arranging algorithm based on particle swarm heredity - Google Patents
Network slice arranging algorithm based on particle swarm heredity Download PDFInfo
- Publication number
- CN114466407A CN114466407A CN202210003854.XA CN202210003854A CN114466407A CN 114466407 A CN114466407 A CN 114466407A CN 202210003854 A CN202210003854 A CN 202210003854A CN 114466407 A CN114466407 A CN 114466407A
- Authority
- CN
- China
- Prior art keywords
- network slice
- network
- algorithm
- particle swarm
- scheme
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000002245 particle Substances 0.000 title claims abstract description 63
- 230000002068 genetic effect Effects 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000013507 mapping Methods 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 210000000349 chromosome Anatomy 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000000034 method Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
- H04W28/09—Management thereof
- H04W28/0925—Management thereof using policies
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a network slice arranging algorithm based on particle swarm heredity.A network slice controller firstly carries out security authentication and service query; then analyzing and processing to obtain information such as service type, service requirement, network resource use condition and the like; after obtaining an available resource set, the network slice orchestrator generates an initial feasible solution by using a genetic algorithm, then outputs an optimal network slice orchestration scheme by using a particle swarm optimization algorithm, and feeds back a network instance identifier to a corresponding service to complete service loading; and finally, collecting network state information such as link bandwidth according to the current ship building network condition, calculating the residual available bandwidth capacity of the link, distinguishing a judgment threshold value of large and small flows, and sending the threshold value to an edge layer switch. The invention combines the globality of the genetic algorithm with the high efficiency of the particle swarm optimization algorithm, improves the convergence speed of the algorithm and can effectively solve the optimal network slice arrangement scheme.
Description
Technical Field
The invention belongs to the technical field of network slicing, and particularly relates to a network slicing arrangement algorithm based on particle swarm heredity.
Background
The diversified development of the network architecture is an important characteristic of 5G, and the network slice is an important technology for realizing the diversified architecture. With the continuous development of network function virtualization (NFV/nfvi) (network Functions virtualization) technology and software Defined network (sdn) (software Defined network) technology, network slicing technology is gradually showing its value and meaning.
Network virtualization technology in network slices decouples network functions from the underlying physical infrastructure, changing the architecture and architecture of traditional networks. The business roles that can be found for network slicing according to the network slicing architecture mainly include 3 for infrastructure provider, virtual network operator and service provider. The infrastructure provider is responsible for deployment, operation and maintenance of basic settings of a bottom-layer physical network, and provides resources to a third party in a leasing mode; the virtual network operator deploys and maps the virtual network according to the actual service request, and operates and maintains the created virtual network; the service provider is directly oriented to the user and provides end-to-end service for the user. In other words, the service request is submitted by the service provider as a request to the virtual network, which further requests network resources from the underlying physical network infrastructure, requiring that constraints with node and link resources be met. The process of allocating underlying physical infrastructure provider Network resources for a virtual Network request according to node constraints, link constraints, and the like is called a virtual Network mapping (vnm) or virtual Network embedding (vne) problem, which is a Non-Deterministic Polynomial NP-hard (Non-Deterministic Polynomial) problem.
The network slice orchestration problem is essentially a mapping problem of network slices on the NFVI. Current research on the virtual network mapping problem is both a focus and a hot spot, and is one of the main challenges facing current researchers. The virtual network mapping problem may be classified according to whether the resource request of the service is known or unknown, the VNE problem of the known service resource request is referred to as static mapping, and correspondingly, the VNE problem of the unknown service resource request is referred to as dynamic mapping problem. The static mapping problem can be divided into a one-stage mapping problem and a two-stage mapping problem according to the mapping sequence of the node link, and the dynamic mapping problem comprises a network mapping dynamic strategy and a reconfiguration problem of the virtual network. Corresponding to the virtual network mapping problem, the research of the virtual network mapping algorithm is mainly developed from three aspects of mapping efficiency, mapping reliability and system energy saving. The particle Swarm optimization PSO (particle Swarm optimization) can effectively solve various optimization problems, and has the characteristics of short calculation time and fast convergence compared with other metaheuristic algorithms when solving some optimization problems which are difficult to solve. The feasible solution of each problem to be optimized in the particle swarm optimization is a particle evaluated by the fitness function value in the search space. The position of each particle represents a potential solution in a solution space, a random speed moves in the whole solution space, and the position and the speed of the particle are adjusted in a search space according to the experience of the particle and the surrounding particles.
Disclosure of Invention
The invention aims to combine a genetic algorithm and a particle swarm algorithm, and designs a network slicing arrangement algorithm, thereby reducing network congestion and improving the utilization rate of network resources.
In order to realize the purpose of the invention, the invention provides a network slice arrangement algorithm based on particle swarm heredity, which is used for designing and arranging network slices of different systems for ship construction to realize load balance and comprises the following steps:
step 1, after a service loading request is initiated, a network slice controller firstly carries out security authentication and service inquiry to ensure the identity of a user and the validity of the request;
step 2, after passing the authentication, the network slice controller carries out analysis processing to obtain service type, service requirement and service condition information of network resources, and the information is delivered to the network slice orchestrator;
step 3, after the network slice orchestrator obtains an available resource set, generating an initial feasible solution by using a genetic algorithm, outputting an optimal network slice orchestration scheme by using a particle swarm optimization algorithm, completing network orchestration instantiation, feeding back a network instance identifier to a corresponding ship building production service, and completing service loading;
step 4, collecting network state information such as link bandwidth according to the current ship building network condition, and calculating the residual available bandwidth capacity of the link; and calculating a judgment threshold value for distinguishing large and small flows according to the average residual available bandwidth capacity of the link, and then sending the threshold value to the edge layer switch.
Furthermore, the network slice orchestrator adopts a self-adaptive dynamic routing algorithm and a polling routing algorithm to adapt to the characteristic that different flows have different requirements on transmission performance, so that the calculation overhead of the controller and the processing time of small flows are reduced.
Further, when finding that a new network slice needs to be established in step 2, the network slice orchestrator divides the required dedicated and multiplexed resource pools for the remaining resources of the network.
Further, the specific steps of generating an initial feasible solution by using a genetic algorithm in the step 3, and then outputting an optimal network slice arranging scheme by using a particle swarm optimization algorithm are as follows:
step a1, initializing relevant data of a ship, and initializing a network slice particle swarm based on a preset network performance index, wherein the network slice particle swarm comprises a plurality of network slice individuals; setting the particle swarm size, the maximum iteration times, the position and the speed of each particle and the initial position of each particle; the particle position vector in the algorithm represents the ith deployment arrangement scheme of a network slice request with n virtual network functions; the particle velocity vector represents an adjustment to the deployment orchestration scheme;
step a2, introducing a genetic algorithm, and generating an initial feasible solution of the network slice arranging scheme through the genetic algorithm;
step a3, calculating the fitness value of each network slice individual;
step a4, comparing the local optimal value with the fitness value of each network slice individual, and replacing the local optimal value if the fitness value is larger;
step a5, comparing the global optimum value with the fitness value of each network slice individual, and replacing the global optimum value if the fitness value is larger;
step a6, updating the speed and the position of the network slice individual;
step a7, if reaching the preset maximum iteration number or meeting the optimal network slice arrangement scheme, exiting, otherwise returning to a 3.
Further, in step a1, the particle swarm size N and the iteration upper limit number M are set, and the initial particle velocity vector is randomly generated.
Further, the step a2 includes the following steps:
step a2-1, firstly, carrying out chromosome coding to generate an initial population; specifically, for each virtual Network function vnf (virtual Network function), a corresponding mapping candidate table is first generated; then scanning all bottom resource nodes, judging whether the resource available amount of the bottom node meets the resource request of the VNF, and if so, adding the bottom node into a mapping candidate table corresponding to the VNF; finally, the bottom nodes in the table are sorted from small to large according to the resource utilization rate or the available resource quantity;
step a2-2, judging whether the stop criterion is met; in the genetic algorithm, a set maximum population evolution algebra is adopted as a stopping criterion; outputting the optimal decoding of the solved problem when reaching the maximum evolution algebra, otherwise continuing iterative evolution, and setting the maximum evolution value according to the population size;
step a2-3, if the stopping criterion is met, decoding and outputting, otherwise, evaluating the fitness of individuals in the population; calculating the fitness values of all individuals in the population according to the fitness function;
step a2-4, carrying out genetic operation;
and a step a2-5, updating the population.
Further, in step a3, a global optimal solution of the network slicing arrangement scheme is initializedgbestAnd a locally optimal solution pibest(ii) a Calculating a fitness function f (X) of each network slice arrangement schemei) Recording the network slice arrangement scheme with the minimum fitness function value as a global optimal arrangement scheme gbestThe locally optimal arrangement scheme of each network slice is pibest＝Xi，XiRefers to the location of the ith network slice orchestration scheme in the search space.
Further, in steps a4 and a5, the current iteration number is added with 1, and the fitness value of each network slicing arrangement scheme is recalculated if f (X)i)＜f(pibest) Updating the local optimal solution p of the network slice arrangement schemeibest＝Xi(ii) a If f (X)i)＜f(gbest) Updating global optimal solution g of network slice arrangement schemebest＝Xi，XiRefers to the location of the ith network slice orchestration scheme in the search space.
Further, in step a6, the speed and position of each network slicing scheme are updated, and the feasibility of the adjusted network slicing scheme (whether there is a path with a bandwidth not less than the bandwidth of the virtual link in all the shortest paths existing between the adjusted physical node and its nodes before and after the adjusted physical node) is checked, and the position vector and the speed vector are re-initialized for the infeasible network slicing scheme.
Further, in step a7, after the iteration loop exit condition is satisfied, the loop exits, and the optimal network slice deployment and arrangement scheme is output.
Compared with the prior art, the invention has the remarkable improvements that: the slice mapping problem needs to solve the optimal mapping node and link from all bottom resource nodes of the bottom network, so that the problem is large in solving scale and high in requirement on the global property of the solution. The accurate solution can realize optimal deployment and arrangement, but the algorithm has high complexity and long execution time, and is not suitable for a network with larger scale in a ship building scene. The invention combines the genetic algorithm and the particle swarm optimization algorithm, combines the globality of the genetic algorithm and the high efficiency of the particle swarm optimization algorithm, improves the convergence speed of the algorithm, and can effectively solve the optimal network slice arrangement scheme.
To more clearly illustrate the functional characteristics and structural parameters of the present invention, the following description is given with reference to the accompanying drawings and the detailed description.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flow chart of a network slice deployment and arrangement algorithm based on a particle swarm genetic algorithm.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments; all other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a network slice arrangement algorithm based on particle swarm heredity, which is used for designing and arranging network slices of different systems for ship construction to realize load balance and comprises the following steps:
step 1, after a service loading request is initiated, a network slice controller firstly carries out security authentication and service inquiry to ensure the identity of a user and the validity of the request;
step 2, after passing the authentication, the network slice controller carries out analysis processing to obtain service type, service requirement and service condition information of network resources, and the information is delivered to the network slice orchestrator;
step 3, after the network slice orchestrator obtains an available resource set, generating an initial feasible solution by using a genetic algorithm, outputting an optimal network slice orchestration scheme by using a particle swarm optimization algorithm, completing network orchestration instantiation, feeding back a network instance identifier to a corresponding ship building production service, and completing service loading;
step 4, collecting network state information such as link bandwidth according to the current ship building network condition, and calculating the residual available bandwidth capacity of the link; and calculating a judgment threshold value for distinguishing large and small flows according to the average residual available bandwidth capacity of the link, and then sending the threshold value to the edge layer switch.
Specifically, in this embodiment, the network slice orchestrator adopts an adaptive dynamic routing algorithm and a round-robin routing algorithm to adapt to the characteristic that different flows have different requirements on transmission performance, thereby reducing the calculation overhead of the controller and the processing time of small flows.
Specifically, in this embodiment, when it is found that a new network slice needs to be established in step 2, the network slice orchestrator divides the required dedicated and multiplexed resource pools for the remaining resources of the network.
As shown in fig. 1, fig. 1 is a flowchart of a network slice deployment and arrangement algorithm based on a particle swarm genetic algorithm, and the specific steps are as follows:
initializing relevant data of a ship, and initializing a network slice particle swarm based on a preset network performance index, wherein the network slice particle swarm comprises a plurality of network slice individuals; setting the particle swarm size, the maximum iteration times, the position and the speed of each particle and the initial position of each particle; the particle position vector in the algorithm represents the ith deployment arrangement scheme of a network slice request with n virtual network functions; the particle velocity vector represents an adjustment to the deployment orchestration scheme;
step a2, introducing a genetic algorithm, and generating an initial feasible solution of the network slice arranging scheme through the genetic algorithm;
step a3, calculating the fitness value of each network slice individual;
step a4, comparing the local optimal value with the fitness value of each network slice individual, and replacing the local optimal value if the fitness value is larger;
step a5, comparing the global optimum value with the fitness value of each network slice individual, and replacing the global optimum value if the fitness value is larger;
step a6, updating the speed and the position of the network slice individual;
step a7, if reaching the preset maximum iteration number or meeting the optimal network slice arrangement scheme, exiting, otherwise returning to a 3.
Specifically, in the present embodiment, in step a1, the particle group size N and the iteration upper limit number M are set, and the initial velocity vector of the particle is randomly generated.
Specifically, in this embodiment, the step a2 includes the following steps:
step a2-1, firstly, carrying out chromosome coding to generate an initial population; specifically, for each virtual Network function vnf (virtual Network function), a corresponding mapping candidate table is first generated; then scanning all bottom resource nodes, judging whether the resource available amount of the bottom node meets the resource request of the VNF, and if so, adding the bottom node into a mapping candidate table corresponding to the VNF; finally, the bottom nodes in the table are sorted from small to large according to the resource utilization rate or the available resource quantity;
step a2-2, judging whether the stop criterion is met; in the genetic algorithm, a set maximum population evolution algebra is adopted as a stopping criterion; outputting the optimal decoding of the solved problem when reaching the maximum evolution algebra, otherwise continuing iterative evolution, and setting the maximum evolution value according to the population size;
step a2-3, if the stopping criterion is met, decoding and outputting, otherwise, evaluating the fitness of individuals in the population; calculating the fitness values of all individuals in the population according to the fitness function;
step a2-4, carrying out genetic operation;
and a step a2-5, updating the population.
Specifically, in the present embodiment, in step a3, a global optimal solution g of the network slicing arrangement scheme is initializedbestAnd a locally optimal solution pibest(ii) a Calculating a fitness function f (X) of each network slice arrangement schemei) Recording the network slice arrangement scheme with the minimum fitness function value as a global optimal arrangement scheme gbestLocal to each network sliceThe optimal arrangement scheme is pibest＝Xi，XiRefers to the location of the ith network slice orchestration scheme in the search space.
Specifically, in this embodiment, in steps a4 and a5, the current iteration number is added by 1, and the fitness value of each network slice arrangement scheme is recalculated if f (X)i)＜f(pibest) Updating the local optimal solution p of the network slice arrangement schemeibest＝Xi(ii) a If f (X)i)＜f(gbest) Updating global optimal solution g of network slice arrangement schemebest＝Xi，XiRefers to the location of the ith network slice orchestration scheme in the search space.
Specifically, in the present embodiment, in step a6, the speed and position of each network slicing arrangement are updated, and the feasibility of the adjusted network slicing arrangement (whether there is a path with a bandwidth not less than the bandwidth of the virtual link among all shortest paths existing between the adjusted physical node and its nodes before and after the adjusted physical node) is checked, and the position vector and the speed vector are reinitialized for the infeasible network slicing arrangement.
Specifically, in this embodiment, in step a7, after the iteration loop exit condition is satisfied, the loop exits, and the optimal network slice deployment and deployment schedule is output.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A network slice arrangement algorithm based on particle swarm heredity is characterized in that different modes of network slice design and arrangement are carried out on ship construction, and load balance is achieved, and the network slice arrangement algorithm specifically comprises the following steps:
step 1, after a service loading request is initiated, a network slice controller firstly carries out security authentication and service inquiry to ensure the identity of a user and the validity of the request;
step 2, after passing the authentication, the network slice controller carries out analysis processing to obtain service type, service requirement and service condition information of network resources, and the information is delivered to the network slice orchestrator;
step 3, after the network slice orchestrator obtains an available resource set, generating an initial feasible solution by using a genetic algorithm, outputting an optimal network slice orchestration scheme by using a particle swarm optimization algorithm, completing network orchestration instantiation, feeding back a network instance identifier to a corresponding ship building production service, and completing service loading;
step 4, collecting link bandwidth network state information according to the current ship building network condition, and calculating the residual available bandwidth capacity of the link; and calculating a judgment threshold value for distinguishing large and small flows according to the average residual available bandwidth capacity of the link, and then sending the threshold value to the edge layer switch.
2. The particle swarm inheritance-based network slice orchestration algorithm of claim 1, wherein the network slice orchestrator employs an adaptive dynamic routing algorithm and a round-robin routing algorithm to adapt to the characteristic that different streams have different requirements for transmission performance, thereby reducing controller computation overhead and streamlet processing time.
3. The particle swarm inheritance based network slice orchestration algorithm according to claim 1, wherein in step 2, when a new network slice needs to be established, the network slice orchestrator partitions the required dedicated and multiplexed resource pool for the remaining resources of the network.
4. The network slice arranging algorithm based on particle swarm inheritance according to claim 1, wherein the genetic algorithm is adopted to generate an initial feasible solution in step 3, and then the particle swarm optimization algorithm is utilized to output an optimal network slice arranging scheme, which comprises the following specific steps:
a1, initializing relevant data of a ship, and initializing a network slice particle swarm based on a preset network performance index, wherein the network slice particle swarm comprises a plurality of network slice individuals; setting the particle swarm size, the maximum iteration times, the position and the speed of each particle and the initial position of each particle; the particle position vector in the algorithm represents the ith deployment arrangement scheme of a network slice request with n virtual network functions; the particle velocity vector represents an adjustment to the deployment orchestration scheme;
step a2, introducing a genetic algorithm, and generating an initial feasible solution of the network slice arranging scheme through the genetic algorithm;
step a3, calculating the fitness value of each network slice individual;
step a4, comparing the local optimal value with the fitness value of each network slice individual, and replacing the local optimal value if the fitness value is larger;
step a5, comparing the global optimum value with the fitness value of each network slice individual, and replacing the global optimum value if the fitness value is larger;
step a6, updating the speed and the position of the network slice individual;
step a7, if reaching the preset maximum iteration number or meeting the optimal network slice arrangement scheme, exiting, otherwise returning to a 3.
5. The algorithm for organizing network slices based on particle swarm inheritance of claim 4, wherein in the step a1, the particle swarm size N and the iteration upper limit number M are set, and the initial velocity vector of the particle is randomly generated.
6. The particle swarm inheritance-based network slicing algorithm according to claim 4, wherein the step a2 comprises the following steps:
step a2-1, firstly, carrying out chromosome coding to generate an initial population; specifically, for each virtual network function VNF, a corresponding mapping candidate table is first generated; then scanning all bottom resource nodes, judging whether the resource available amount of the bottom node meets the resource request of the VNF, and if so, adding the bottom node into a mapping candidate table corresponding to the VNF; finally, the bottom nodes in the table are sorted from small to large according to the resource utilization rate or the available resource quantity;
step a2-2, judging whether the stop criterion is met; in the genetic algorithm, a set maximum population evolution algebra is adopted as a stopping criterion; outputting the optimal decoding of the solved problem when reaching the maximum evolution algebra, otherwise continuing iterative evolution, and setting the maximum evolution value according to the population size;
step a2-3, if the stopping criterion is met, decoding and outputting, otherwise, evaluating the fitness of individuals in the population; calculating the fitness values of all individuals in the population according to the fitness function;
step a2-4, carrying out genetic operation;
and a step a2-5, updating the population.
7. The particle swarm genetic network slicing algorithm according to claim 4, wherein in step a3, the global optimal solution g of the network slicing algorithm is initializedbestAnd a locally optimal solution pibest(ii) a Calculating a fitness function f (X) of each network slice arrangement schemei) Recording the network slice arrangement scheme with the minimum fitness function value as a global optimal arrangement scheme gbestThe locally optimal arrangement scheme of each network slice is pibest＝Xi，XiMeans that the ith network slice editing scheme is searchingPosition in space.
8. The particle swarm genetic network slicing algorithm according to claim 4, wherein in steps a4 and a5, the current iteration number is added to 1, and the fitness value of each network slicing scheme is recalculated if f (X)i)＜f(pibest) Updating the local optimal solution p of the network slice arrangement schemeibest＝Xi(ii) a If f (X)i)＜f(gbest) Updating global optimal solution g of network slice arrangement schemebest＝Xi，XiRefers to the location of the ith network slice orchestration scheme in the search space.
9. The particle swarm inheritance based network slicing algorithm as claimed in claim 4, wherein in step a6, the speed and position of each network slicing scheme are updated, and the feasibility of the adjusted network slicing scheme is checked, that is, whether a path with bandwidth not less than the bandwidth of the virtual link exists in all shortest paths existing between the adjusted physical node and its nodes before and after the adjusted physical node is determined, and the position vector and the speed vector are reinitialized for the infeasible network slicing scheme.
10. The particle swarm inheritance-based network slice orchestration algorithm according to claim 4, wherein in step a7, after an iteration loop exit condition is satisfied, the loop exits, and an optimal network slice deployment orchestration scheme is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210003854.XA CN114466407B (en) | 2022-01-04 | 2022-01-04 | Network slice arrangement algorithm based on particle swarm inheritance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210003854.XA CN114466407B (en) | 2022-01-04 | 2022-01-04 | Network slice arrangement algorithm based on particle swarm inheritance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114466407A true CN114466407A (en) | 2022-05-10 |
| CN114466407B CN114466407B (en) | 2024-05-07 |
Family
ID=81406805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210003854.XA Active CN114466407B (en) | 2022-01-04 | 2022-01-04 | Network slice arrangement algorithm based on particle swarm inheritance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114466407B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116347404A (en) * | 2023-05-30 | 2023-06-27 | 天翼云科技有限公司 | Group authentication-based mMTC network slice mapping method and system |
| CN116545853A (en) * | 2023-07-04 | 2023-08-04 | 南京理工大学 | Integrated network multi-objective optimized resource management method based on quantum particle swarm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132148A1 (en) * | 2011-11-07 | 2013-05-23 | Ecole Polytechnique Federale De Lausanne (Epfl) | Method for multi-objective quality-driven service selection |
| CN108174394A (en) * | 2018-01-12 | 2018-06-15 | 西安邮电大学 | A kind of Arrangement algorithm of 5G networks slice |
| CN109995580A (en) * | 2019-03-13 | 2019-07-09 | 北京工业大学 | VN mapping method based on GA_PSO hybrid algorithm in 5G network slice |
| CN111107557A (en) * | 2019-12-09 | 2020-05-05 | 中国船舶重工集团公司第七一六研究所 | Private network deployment method, device and system based on 5G communication standard |
| CN111510334A (en) * | 2020-04-21 | 2020-08-07 | 中国电子科技集团公司第五十四研究所 | Particle swarm algorithm-based VNF online scheduling method |
| WO2020181761A1 (en) * | 2019-03-11 | 2020-09-17 | 江苏君英天达人工智能研究院有限公司 | Sdn enhanced path allocation device and method employing bin-packing technique |
-
2022
- 2022-01-04 CN CN202210003854.XA patent/CN114466407B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132148A1 (en) * | 2011-11-07 | 2013-05-23 | Ecole Polytechnique Federale De Lausanne (Epfl) | Method for multi-objective quality-driven service selection |
| CN108174394A (en) * | 2018-01-12 | 2018-06-15 | 西安邮电大学 | A kind of Arrangement algorithm of 5G networks slice |
| WO2020181761A1 (en) * | 2019-03-11 | 2020-09-17 | 江苏君英天达人工智能研究院有限公司 | Sdn enhanced path allocation device and method employing bin-packing technique |
| CN109995580A (en) * | 2019-03-13 | 2019-07-09 | 北京工业大学 | VN mapping method based on GA_PSO hybrid algorithm in 5G network slice |
| CN111107557A (en) * | 2019-12-09 | 2020-05-05 | 中国船舶重工集团公司第七一六研究所 | Private network deployment method, device and system based on 5G communication standard |
| CN111510334A (en) * | 2020-04-21 | 2020-08-07 | 中国电子科技集团公司第五十四研究所 | Particle swarm algorithm-based VNF online scheduling method |
Non-Patent Citations (1)
| Title |
|---|
| 朱华;吴礼发;赵鹏;: "多云环境的虚拟应用网络部署决策方法研究", 计算机科学, no. 2, 15 November 2017 (2017-11-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116347404A (en) * | 2023-05-30 | 2023-06-27 | 天翼云科技有限公司 | Group authentication-based mMTC network slice mapping method and system |
| CN116347404B (en) * | 2023-05-30 | 2023-10-13 | 天翼云科技有限公司 | Group authentication-based mMTC network slice mapping method and system |
| CN116545853A (en) * | 2023-07-04 | 2023-08-04 | 南京理工大学 | Integrated network multi-objective optimized resource management method based on quantum particle swarm |
| CN116545853B (en) * | 2023-07-04 | 2023-10-13 | 南京理工大学 | Integrated network multi-objective optimized resource management method based on quantum particle swarm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114466407B (en) | 2024-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Resource provision algorithms in cloud computing: A survey | |
| CN109981438B (en) | Satellite network load balancing method oriented to SDN and NFV collaborative deployment framework | |
| Kar et al. | Offloading using traditional optimization and machine learning in federated cloud–edge–fog systems: A survey | |
| WO2020258920A1 (en) | Network slice resource management method and apparatus | |
| CN105979007B (en) | Method and device for accelerating resource processing and network function virtualization system | |
| WO2017214932A1 (en) | Network-slice resource management method and apparatus | |
| Wang et al. | Towards network-aware service composition in the cloud | |
| CN114466407B (en) | Network slice arrangement algorithm based on particle swarm inheritance | |
| CN104115165A (en) | Method for mapping media components employing machine learning | |
| CN111130858B (en) | Dynamic multi-target virtual network mapping method in SD-WAN scene | |
| CN108897606B (en) | Self-adaptive scheduling method and system for virtual network resources of multi-tenant container cloud platform | |
| Wang et al. | Presto: Towards efficient online virtual network embedding in virtualized cloud data centers | |
| CN115529316B (en) | Micro-service deployment method based on cloud computing center network architecture | |
| CN107103360B (en) | Reliable application distribution distributed genetic method based on mixed cloud | |
| Meneguette et al. | An efficient green-aware architecture for virtual machine migration in sustainable vehicular clouds | |
| CN113472671A (en) | Method and device for determining multicast route and computer readable storage medium | |
| Satpathy et al. | CoMap: An efficient virtual network re-mapping strategy based on coalitional matching theory | |
| Ibrahim et al. | A modified genetic algorithm for controller placement problem in SDN distributed network | |
| Saravanan et al. | Improving map reduce task scheduling and micro-partitioning mechanism for mobile cloud multimedia services | |
| Lovén et al. | Weathering the reallocation storm: Large-scale analysis of edge server workload | |
| CN114978913B (en) | Cross-domain deployment method and system for service function chains based on cut chains | |
| Wang et al. | An efficient framework for online virtual network embedding in virtualized cloud data centers | |
| CN113596146B (en) | Resource scheduling method and device based on big data | |
| Midya et al. | An adaptive resource placement policy by optimizing live VM migration for ITS applications in vehicular cloud network | |
| He et al. | QoS-Aware and Resource-Efficient Dynamic Slicing Mechanism for Internet of Things. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 222001 No.18 Shenghu Road, Lianyungang City, Jiangsu Province Applicant after: The 716th Research Institute of China Shipbuilding Corp. Address before: 222001 No.18 Shenghu Road, Lianyungang City, Jiangsu Province Applicant before: 716TH RESEARCH INSTITUTE OF CHINA SHIPBUILDING INDUSTRY Corp. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |